Training in progress, epoch 1

config.json

@@ -7,14 +7,14 @@
   "gradient_checkpointing": false,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "hidden_size": 512,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,
   "model_type": "bert",
   "num_attention_heads": 16,
-  "num_hidden_layers": 6,
+  "num_hidden_layers": 12,
   "pad_token_id": 0,
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4a2ed46520bccc990ef9e34fbb9dae08b964dfa763e84fd3dcea1d9356a6aa9
-size 267862062
+oid sha256:5a06fd3f8f7eeb33fd98d6c5f92aad1f237eeb1b9b88eb9e393dd1520a3de4b4
+size 266384622

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 512,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 512
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 0,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 0,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b835269f5106d51469a74a58d92bdc2d43bc14bc6ac6eefd291acd4e2d2082d
+oid sha256:7275062ee42c51ae3b22367e14409f8b39e1a2299bfc3f1a16fb50b43919d201
 size 4600